SELECTIVE CATALYTIC REDUCTION STUDYING SYSTEM AND STUDYING METHOD OF SELECTIVE CATALYTIC REDUCTION

摘要

The present invention relates to a selective catalytic reduction learning system and a selective catalytic reduction learning method, wherein the selective catalytic reduction learning system according to an embodiment of the present invention is supplied to a reactor in which a catalyst for reducing nitrogen oxides contained in exhaust gas is installed a first input variable unit to which a first input variable including a flow rate of the exhaust gas is input; an output variable unit for inputting an output variable for the concentration of nitrogen oxide contained in the purification gas from which the exhaust gas has been purified by the catalytic reduction reaction in the reactor; and a calculator configured to calculate a regression coefficient learned based on an artificial neural network using a first input variable input from the first input variable unit and an output variable input from the output variable unit, and to build a learning model, wherein the The calculating unit may use the regression coefficient and the learning model in the process of calculating the input amount of the reducing agent to be input to make the catalytic reduction reaction in the reactor. According to the present invention, it is possible to learn and pattern the injection amount of the reducing agent supplied to each channel of the reactor, and thereby determine the situation in the device in real time and actively control the injection amount, thereby increasing the efficiency of reducing nitrogen oxides, and reducing the reducing agent leakage can be minimized.